How it works.
One loop, end to end.
Most of this site is output. This page is the engine that produces it — a single closed loop where questions become autonomous research, findings link into a knowledge graph, synthesis finds the cross-domain connections, and the patterns that prove out get written back as rules. Each pass makes the next one sharper.
One closed loop. It improves itself every cycle.
Questions go in, autonomous agents research them, findings link into a knowledge graph, synthesis finds the cross-domain connections, and the patterns that prove out become rules that sharpen the next cycle. Hover or tap a stage to see what it actually does — annotated with live counts from the vault, not hand-typed.
Intent
Everything starts as raw input — real prompts, project goals, and open questions. These are the seeds the engine pulls through the rest of the loop.
The center is the nervous system — a neural router and a heartbeat scheduler keeping 170 tasks and 2 autonomous loops in step. The same engine is applied across 12 industries and 19 shipped apps.
Data as of 2026-06-03
One step of the loop, live in your browser. Fifteen specialized agent profiles (“neurons”) compete to handle each task; the winner loads its own context and conventions. Type anything and watch them activate.
The vault auto-detects mode from your wording. Flip it manually to watch the neuromodulators re-weight whole classes of neurons.
Routes to Debugger
What you're driving is the deterministic keyword tier of the real router, running entirely in your browser — the exact scoring from neural-router.py (task-type keywords count 3×, domain nouns 1× with diminishing returns, negative-keyword penalties, per-mode neuromodulator gains, and a “task-type beats domain noun” pass). The vault reports this tier at ~87% on its own. The live system (~98% reported) adds a Claude Haiku tie-break for ambiguous cases, plus cross-message hysteresis and a learning loop — those run server-side and aren't in this replica. More on the engine.
A workflow, not a model
Markdown is the substrate
Honest about the seams
This page is the narrative. The live numbers, dashboards, and backing knowledge base live on their own pages — annotated with the same real counts the loop above reads from 15,884+ notes and 164 autonomous tasks.
The map of every moving part with current status — start here to pick the right next click.
A near-real-time view of what the autonomous loops are doing right now.
The knowledge engine itself — the graph, the notes, and the search that the loop reads and writes.
The operating model behind it: model hierarchy, two-pass review, file-ownership parallelism, self-improving rules.
Want to see what the loop has shipped?